This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
Wikitags
LW
Login
Gears-Level
Settings
Applied to
Will LLM agents become the first takeover-capable AGIs?
by
Seth Herd
2mo
ago
lesswrong-internal
v1.5.0
Feb 8th 2025 GMT
Convert editor type to CkEditor
1
Applied to
Towards building blocks of ontologies
by
Daniel C
3mo
ago
Applied to
Don't want Goodhart? — Specify the variables more
by
YanLyutnev
5mo
ago
Applied to
Don't want Goodhart? — Specify the damn variables
5mo
ago
Applied to
What are the best resources for building gears-level models of how governments actually work?
by
adamShimi
8mo
ago
Applied to
You don't know how bad most things are nor precisely how they're bad.
by
Gunnar_Zarncke
9mo
ago
Applied to
rough draft on what happens in the brain when you have an insight
by
Emrik
1y
ago
Applied to
Legibility Makes Logical Line-Of-Sight Transitive
by
StrivingForLegibility
1y
ago
Applied to
The Gears of Argmax
by
StrivingForLegibility
1y
ago
Applied to
A Crisper Explanation of Simulacrum Levels
by
Thane Ruthenis
1y
ago
Applied to
A Good Explanation of Differential Gears
by
Ruby
2y
ago
Applied to
Inside Views, Impostor Syndrome, and the Great LARP
by
Adam Zerner
2y
ago
Applied to
A Case for the Least Forgiving Take On Alignment
by
Thane Ruthenis
2y
ago
Applied to
Decision Transformer Interpretability
by
Joseph Bloom
2y
ago
B Jacobs
v1.4.0
Dec 4th 2022 GMT
(
+77
/
-77
)
1
Applied to
Current themes in mechanistic interpretability research
by
Lee Sharkey
2y
ago
Applied to
Value Formation: An Overarching Model
by
Thane Ruthenis
2y
ago
Applied to
A Sketch of Good Communication
by
Emrik
3y
ago
Applied to
Towards Gears-Level Understanding of Agency
by
Thane Ruthenis
3y
ago